• rumschlumpel@feddit.org
    link
    fedilink
    arrow-up
    7
    ·
    13 hours ago

    You people are buying proper homeservers? I thought everyone just used old desktop PCs and single board computers.

  • dubs@lemmy.dbzer0.com
    link
    fedilink
    arrow-up
    16
    ·
    edit-2
    22 hours ago

    I’m not going to say that I don’t have a server-collection problem, but that problem did put me on a good career path, so at least I have that going for me.

  • CubitOom@infosec.pub
    link
    fedilink
    English
    arrow-up
    14
    ·
    21 hours ago

    Access to knowledge and ability to maintain ownership gives you freedom, confidence, and a desire to expand.

    • underisk@lemmy.ml
      link
      fedilink
      arrow-up
      11
      ·
      19 hours ago

      Pretty sure it’s from Serial Experiments Lain, a show I’ve heard much about but haven’t watched yet so I’m not 100% certain about this.

      • toynbee@piefed.social
        link
        fedilink
        English
        arrow-up
        2
        ·
        edit-2
        14 hours ago

        TY!

        edit: Seems you’re correct. however Real Life Comics had at least one strip about how, iirc, the protagonist introduced his girlfriend to Linux and the next week she was building a Beowulf cluster. The visuals were not dissimilar to this, but RLC is difficult to search in my experience.

    • Mika@piefed.ca
      link
      fedilink
      English
      arrow-up
      2
      ·
      17 hours ago

      128 gb uram 🤤

      Fucking saved.

      Do you know what kind of open weights it can run, and at which t/s?

      • TropicalDingdong@lemmy.world
        link
        fedilink
        arrow-up
        0
        ·
        17 hours ago

        Yeah I can run any open weight models which leave me enough vram to not crash. But its a bit of a gotcha because you also need enough system ram to load the model. I use it to heavily parallelize training tasks… Honestly, I need to tinker with it more but I’m pretty annoyed at how ollama has gone deep in the paint as basically being a tool for accessing cloud models.

        Someday TM

          • TropicalDingdong@lemmy.world
            link
            fedilink
            arrow-up
            1
            ·
            1 hour ago

            Mostly time. I didn’t buy the machine to run someone else’s models. I bought it to run my own models and the machine has a job to do. Tinkering with self hosting llms, I guess. I appreciate them as models. But my machine has a day job.

        • dubs@lemmy.dbzer0.com
          link
          fedilink
          arrow-up
          1
          ·
          14 hours ago

          I’m pretty annoyed at how ollama has gone deep in the paint as basically being a tool for accessing cloud models.

          Can you expound a little more on what you mean by this?

          I like ollama, but I only really use it to load models and then hit the API. My current issue with them is that they don’t seem to support non-text base interaction very well.

      • TropicalDingdong@lemmy.world
        link
        fedilink
        arrow-up
        4
        ·
        21 hours ago

        Yeah I’ve got the 128 gb Asus one as a processing machine, and honestly, I wish I would have just got it as a server. For my purposes, I need this bad-ass GPU/ CPU much closer to the storage.

        Honestly, just a basic 2:1 is fine for me considering I’m rarely if ever running my compute locally.

        • tatterdemalion@programming.dev
          link
          fedilink
          arrow-up
          3
          ·
          20 hours ago

          I’m not sure I need a lot of compute on my NAS. I guess I might as well get as much as I can before it becomes cost prohibitive. Not planning on running any local LLMs on it though, so a GPU is probably overkill.

          • TropicalDingdong@lemmy.world
            link
            fedilink
            arrow-up
            4
            ·
            20 hours ago

            Yeah I do a ton of machine learning research and like, distance between the database and the place I’m doing the processing really matters. My NAS is on the other side of my house and it would be great to have maybe two NAS, a primary one for like, my movies, personal files, old projects etc, and then this one right next to it for active projects.

            Right now I’m having to do it all on my primary machine, which means I often have to freeze updates for long periods of time once I get a particular compute configuration set up for a particular project.

  • palordrolap@fedia.io
    link
    fedilink
    arrow-up
    5
    ·
    21 hours ago

    Curious. I must be a filthy casual with the one desktop PC. There is at least one other PC here, but it’s out of action.

    It could do with plugging in at some point to see if it still works, but I see no benefit in making that permanent.